|
--- |
|
license: apache-2.0 |
|
base_model: facebook/deit-tiny-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smids_3x_deit_tiny_adamax_001_fold2 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: test |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8935108153078203 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# smids_3x_deit_tiny_adamax_001_fold2 |
|
|
|
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9522 |
|
- Accuracy: 0.8935 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.5261 | 1.0 | 225 | 0.3629 | 0.8552 | |
|
| 0.3081 | 2.0 | 450 | 0.3850 | 0.8303 | |
|
| 0.2433 | 3.0 | 675 | 0.4084 | 0.8486 | |
|
| 0.2976 | 4.0 | 900 | 0.3348 | 0.8752 | |
|
| 0.2892 | 5.0 | 1125 | 0.3154 | 0.8752 | |
|
| 0.1338 | 6.0 | 1350 | 0.4213 | 0.8586 | |
|
| 0.1811 | 7.0 | 1575 | 0.4568 | 0.8602 | |
|
| 0.1262 | 8.0 | 1800 | 0.4156 | 0.8702 | |
|
| 0.1405 | 9.0 | 2025 | 0.4962 | 0.8552 | |
|
| 0.1378 | 10.0 | 2250 | 0.4880 | 0.8652 | |
|
| 0.0783 | 11.0 | 2475 | 0.5529 | 0.8602 | |
|
| 0.1156 | 12.0 | 2700 | 0.5059 | 0.8569 | |
|
| 0.0435 | 13.0 | 2925 | 0.5510 | 0.8735 | |
|
| 0.06 | 14.0 | 3150 | 0.5625 | 0.8669 | |
|
| 0.0749 | 15.0 | 3375 | 0.6173 | 0.8719 | |
|
| 0.0723 | 16.0 | 3600 | 0.5869 | 0.8785 | |
|
| 0.0343 | 17.0 | 3825 | 0.6758 | 0.8852 | |
|
| 0.0074 | 18.0 | 4050 | 0.7248 | 0.8686 | |
|
| 0.0351 | 19.0 | 4275 | 0.6545 | 0.8785 | |
|
| 0.0367 | 20.0 | 4500 | 0.7634 | 0.8785 | |
|
| 0.0039 | 21.0 | 4725 | 0.8073 | 0.8752 | |
|
| 0.0183 | 22.0 | 4950 | 0.6969 | 0.8869 | |
|
| 0.015 | 23.0 | 5175 | 0.7193 | 0.8885 | |
|
| 0.0003 | 24.0 | 5400 | 0.8406 | 0.8719 | |
|
| 0.0461 | 25.0 | 5625 | 0.8687 | 0.8702 | |
|
| 0.0004 | 26.0 | 5850 | 0.7424 | 0.8802 | |
|
| 0.0001 | 27.0 | 6075 | 0.8481 | 0.8819 | |
|
| 0.0001 | 28.0 | 6300 | 0.8060 | 0.8785 | |
|
| 0.0003 | 29.0 | 6525 | 0.8316 | 0.8869 | |
|
| 0.0012 | 30.0 | 6750 | 0.8183 | 0.8835 | |
|
| 0.007 | 31.0 | 6975 | 0.7519 | 0.8802 | |
|
| 0.0 | 32.0 | 7200 | 0.8429 | 0.8852 | |
|
| 0.002 | 33.0 | 7425 | 0.8340 | 0.8885 | |
|
| 0.0 | 34.0 | 7650 | 0.8626 | 0.8785 | |
|
| 0.0 | 35.0 | 7875 | 0.8155 | 0.8935 | |
|
| 0.0035 | 36.0 | 8100 | 0.8392 | 0.8918 | |
|
| 0.0 | 37.0 | 8325 | 0.9154 | 0.8852 | |
|
| 0.0 | 38.0 | 8550 | 0.9252 | 0.8885 | |
|
| 0.0047 | 39.0 | 8775 | 0.9247 | 0.8852 | |
|
| 0.0 | 40.0 | 9000 | 0.9286 | 0.8918 | |
|
| 0.0 | 41.0 | 9225 | 0.9340 | 0.8902 | |
|
| 0.0 | 42.0 | 9450 | 0.9212 | 0.8885 | |
|
| 0.0 | 43.0 | 9675 | 0.9298 | 0.8902 | |
|
| 0.0 | 44.0 | 9900 | 0.9334 | 0.8935 | |
|
| 0.0 | 45.0 | 10125 | 0.9402 | 0.8952 | |
|
| 0.0 | 46.0 | 10350 | 0.9378 | 0.8952 | |
|
| 0.0 | 47.0 | 10575 | 0.9454 | 0.8918 | |
|
| 0.0 | 48.0 | 10800 | 0.9493 | 0.8935 | |
|
| 0.0024 | 49.0 | 11025 | 0.9513 | 0.8935 | |
|
| 0.0024 | 50.0 | 11250 | 0.9522 | 0.8935 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|